Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 52804
    Prev
    Next
    INDEX
    Explanations

    numbers like four and seven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    0.58
    }[
    0.53
    л
    0.52
    дування
    0.48
     ډول
    0.48
    ě
    0.47
    ן
    0.46
     کنید
    0.45
    ډ
    0.45
     څه
    0.44
    POSITIVE LOGITS
     Seven
    0.66
     fours
    0.66
     hundred
    0.65
     Hundred
    0.60
     Four
    0.59
    Seven
    0.58
     threes
    0.58
    Three
    0.57
     Eight
    0.57
    fourths
    0.57
    Activations Density 0.099%

    No Known Activations